人工智能与人类临床医生在X线片上检测腕部骨折的准确性比较:一项系统评价与荟萃分析
该系统评价与荟萃分析纳入20项研究,比较人工智能与人类读者检测腕部骨折的诊断性能。AI检测桡骨远端骨折的合并敏感度和特异度分别为0.92(95%CI 0.88-0.95)和0.89(0.84-0.92),人类读者为0.95(0.91-0.97)和0.94(0.91-0.96);舟骨骨折AI为0.85(0.73-0.92)和0.83(0.76-0.89),人类专家为0.71(0.66-0.76)和0.93(0.90-0.95)。结论提示AI与人类读者诊断准确性相当,尤其桡骨远端骨折,AI可能增强骨折检测准确性并改善临床工作流程而非替代人类智能。
要点
- AI检测桡骨远端骨折的合并敏感度0.92(95%CI 0.88-0.95)、特异度0.89(0.84-0.92),人类读者分别为0.95(0.91-0.97)和0.94(0.91-0.96)。
- AI检测舟骨骨折的合并敏感度0.85(95%CI 0.73-0.92)、特异度0.83(0.76-0.89),人类专家分别为0.71(0.66-0.76)和0.93(0.90-0.95)。
- AI与人类读者诊断准确性相当,尤其桡骨远端骨折;舟骨骨折人类读者敏感度相似但特异度更高。
核心结论
- AI与人类读者诊断准确性相当,尤其桡骨远端骨折;舟骨骨折人类读者敏感度相似但特异度更高;AI可能增强骨折检测准确性并改善临床工作流程,而非替代人类智能。
研究设计与样本
- 系统评价与荟萃分析,遵循PRISMA指南,检索Medline和Embase截至2023年8月14日,最终纳入20项研究。
诊断标准与关键数值
- AI检测桡骨远端骨折:合并敏感度0.92(95%CI 0.88-0.95),合并特异度0.89(0.84-0.92)。
- 人类读者检测桡骨远端骨折:合并敏感度0.95(95%CI 0.91-0.97),合并特异度0.94(0.91-0.96)。
- AI检测舟骨骨折:合并敏感度0.85(95%CI 0.73-0.92),合并特异度0.83(0.76-0.89)。
- 人类专家检测舟骨骨折:合并敏感度0.71(95%CI 0.66-0.76),合并特异度0.93(0.90-0.95)。
临床应用与阅片要点
- AI与人类读者诊断准确性相当,尤其桡骨远端骨折,可能增强骨折检测准确性并改善临床工作流程,而非替代人类智能。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: The aim of the study is to perform a systematic review and meta-analysis comparing the diagnostic performance of artificial intelligence (AI) and human readers in the detection of wrist fractures.
METHOD: This study conducted a systematic review following PRISMA guidelines. Medline and Embase databases were searched for relevant articles published up to August 14, 2023. All included studies reported the diagnostic performance of AI to detect wrist fractures, with or without comparison to human readers. A meta-analysis was performed to calculate the pooled sensitivity and specificity of AI and human experts in detecting distal radius, and scaphoid fractures respectively.
RESULTS: Of 213 identified records, 20 studies were included after abstract screening and full-text review. Nine articles examined distal radius fractures, while eight studies examined scaphoid fractures. One study included distal radius and scaphoid fractures, and two studies examined paediatric distal radius fractures. The pooled sensitivity and specificity for AI in detecting distal radius fractures were 0.92 (95% CI 0.88-0.95) and 0.89 (0.84-0.92), respectively. The corresponding values for human readers were 0.95 (0.91-0.97) and 0.94 (0.91-0.96). For scaphoid fractures, pooled sensitivity and specificity for AI were 0.85 (0.73-0.92) and 0.83 (0.76-0.89), while human experts exhibited 0.71 (0.66-0.76) and 0.93 (0.90-0.95), respectively.
CONCLUSION: The results indicate comparable diagnostic accuracy between AI and human readers, especially for distal radius fractures. For the detection of scaphoid fractures, the human readers were similarly sensitive but more specific. These findings underscore the potential of AI to enhance fracture detection accuracy and improve clinical workflow, rather than to replace human intelligence.
引用
- Suen K, Zhang R, Kutaiba N, et al. Accuracy of wrist fracture detection on radiographs by artificial intelligence compared to human clinicians. A systematic review and meta-analysis. Eur J Radiol. 2024. PMID: 38981178. doi:10.1016/j.ejrad.2024.111593
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。